mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-31 02:02:21 +06:00
af8afdc88d
* wav2vec2: support datasets other than LibriSpeech * Formatting run_asr.py to pass code quality test * bundled orthography options and added verbose logs * fixing a typo in timit fine-tuning script * update comment for clarity * resize_lm_head and load custom vocab from file * adding a max_duration_in_seconds filter * do not assign `duration_filter` lambda, use a def * log untransliterated text as well * fix base model for arabic * fix duration filter when target_sr is not set * drop duration_in_seconds when unneeded * script for wav2vec2-large-lv60-timit-asr * fix for "tha" in arabic corpus (huggingface#10581) * adding more options to work with common_voice * PR feedback (huggingface#10581) * small README change
58 lines
733 B
JSON
58 lines
733 B
JSON
{
|
|
"<pad>": 0,
|
|
"<s>": 1,
|
|
"</s>": 2,
|
|
"<unk>": 3,
|
|
"/": 4,
|
|
"'": 5,
|
|
"|": 6,
|
|
">": 7,
|
|
"&": 8,
|
|
"<": 9,
|
|
"}": 10,
|
|
"A": 11,
|
|
"b": 12,
|
|
"p": 13,
|
|
"t": 14,
|
|
"v": 15,
|
|
"j": 16,
|
|
"H": 17,
|
|
"x": 18,
|
|
"d": 19,
|
|
"*": 20,
|
|
"r": 21,
|
|
"z": 22,
|
|
"s": 23,
|
|
"$": 24,
|
|
"S": 25,
|
|
"D": 26,
|
|
"T": 27,
|
|
"Z": 28,
|
|
"E": 29,
|
|
"g": 30,
|
|
"_": 31,
|
|
"f": 32,
|
|
"q": 33,
|
|
"k": 34,
|
|
"l": 35,
|
|
"m": 36,
|
|
"n": 37,
|
|
"h": 38,
|
|
"w": 39,
|
|
"Y": 40,
|
|
"y": 41,
|
|
"F": 42,
|
|
"N": 43,
|
|
"K": 44,
|
|
"a": 45,
|
|
"u": 46,
|
|
"i": 47,
|
|
"~": 48,
|
|
"o": 49,
|
|
"`": 50,
|
|
"{": 51,
|
|
"P": 52,
|
|
"J": 53,
|
|
"V": 54,
|
|
"G": 55
|
|
} |